add baseline-100k SFT checkpoint: H3K4me3

NT/H3K4me3/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/home/n5huang/dna_token/pretrain/models/base_5120/checkpoint-100000",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 5120
+}

NT/H3K4me3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb71f4b01ade890349ec3748d2358be9f613fa2fe0c0aa7d6a04ae020da3788
+size 359923616

NT/H3K4me3/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

NT/H3K4me3/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "cache_dir": null,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 220,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "trust_remote_code": true,
+  "unk_token": "[UNK]",
+  "use_fast": true
+}

NT/H3K4me3/trainer_state.json

@@ -0,0 +1,38 @@
+{
+  "best_metric": 0.8381776094567215,
+  "best_model_checkpoint": "/home/n5huang/dna_token/mario/best_hp_runs/Nucleotides_task/output_best_nt_base_5120_rerun/H3K4me3/base_5120/lr3e-5_wd0.01_wr0.10_ep3_seed42/checkpoint-115",
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.370967741935484e-05,
+      "loss": 0.4525,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8382675438596491,
+      "eval_f1": 0.8381776094567215,
+      "eval_loss": 0.37205269932746887,
+      "eval_matthews_correlation": 0.6813132248003785,
+      "eval_precision": 0.8415325697378624,
+      "eval_recall": 0.8397829017040531,
+      "eval_runtime": 1.0994,
+      "eval_samples_per_second": 1659.063,
+      "eval_steps_per_second": 13.644,
+      "step": 115
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 345,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1650045483702000.0,
+  "trial_name": null,
+  "trial_params": null
+}

NT/H3K4me3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e97f512cfd969d5cbfde8e0d3e406681456f300dac0dad223f0e9b55675e71
+size 5457